• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2333-2345
• /
• 2024

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

• Journal of information and communication convergence engineering
• /
• 제3권2호
• /
• pp.110-113
• /
• 2005

An enhancement of tracking capacity for the centering position of eye and iris on the facial image is presented. A facial image is acquisitioned with a CCD camera to be converted into a binary image. The eye region to be a specified brightness and shapes is used the FRM method using the neighboring five mask areas, and the iris on the eye is tracked with FPDP method. The experimental result shows that the proposed methods lead the centering position tracking capability to be enhanced than the pixel average coordinate values method.

• 정보처리학회논문지B
• /
• 제9B권4호
• /
• pp.491-500
• /
• 2002

본 논문에서는 칼라 얼굴 영상으로부터 피부색 정보, 얼굴의 기하학적 특징벡터 및 안면각 정보를 이용한 실시간 얼굴검출 및 인식 알고리즘을 제안하였다. 제안한 알고리즘에서는 HSI 칼라좌표계상의 얼굴 피부색 정보와 얼굴 에지 정보를 함께 이용함으로써 얼굴 영역 검출 효율을 개선하였다. 또한 추출된 얼굴 영역으로부터 얼굴인식율 개선을 위해 얼굴 특징자들을 추출하고 추출된 얼굴 특징자들의 기하학적 관계로 구성된 얼굴 특징벡터와 얼굴 안면각 정보를 사용하여 얼굴 인식율을 개선하였다. 실험에서는 제안한 방법이 기존의 방법에 비해 얼굴 영역 검출율 뿐만 아니라 얼굴 인식율도 개선되었음을 알 수 있다.

• 한국멀티미디어학회논문지
• /
• 제7권1호
• /
• pp.27-34
• /
• 2004

본 논문에서는 컬러 영상에서 색상과 에지 정보를 이용한 얼굴 영역 검출 알고리즘을 제안한다. 제안된 알고리즘은 YCbCr 색공간에서 Cb와 Cr성분을 이용하여 피부색 분할을 한 후에 형태학적 필터링과 레이블링을 통해 얼굴 후보 영역을 분리한다. 분리된 각 후보 영역에 대해 휘도 성분 Y에서 소벨 마스크의 수직 연산자를 적용한 후에 수평 투영을 통해 나타난 최대값을 눈의 위치로 검출해낸다. 비슷하게 얼굴의 지형적인 특징과 소벨 마스크의 수평 연산자를 적용하여 계산된 수평 투영의 최대값에 따라 턱 부분을 검출한다. 실험 결과, 기존의 연구와 검출율을 비슷하면서도 턱의 위치를 검출함으로써 목 부분이 얼굴 영역에 포함되는 것을 방지할 수 있음을 볼 수 있다.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제27권6호
• /
• pp.551-555
• /
• 2001

False aneurysms(Pseudoaneurysms) and arteriovenous fistulas have only rarely been reported in the facial region. In this region the false aneurysm arises most frequently in the superficial temporal and facial artery, but other branches of the external carotid are sometimes involved, including the maxillary and lingual artery. False aneurysms can be occurred by blunt trauma that either laceration or rupture the full thickness of the arterial wall. The diagnosis of a false arterial aneurysm can be often made solely on the basis of physical examination. Angiography is helpful for conformation, for delineating the lesion and its vascular supply, and for ruling out the presence of associated vascular lesions such as arteriovenous fistulas. Ultrasonography may also be useful in delineating lesions that are not easily accessible for physical examination. Treatment of false aneurysms is excision, ligation, and arterial embolization. This is a case of false aneurysm of the lingual artery after facial trauma caused by traffic accident. The lesion was successfully treated by embolization and ligation of the lingual and facial branches of the external carotid artery.

• 대한치과교정학회지
• /
• 제24권4호
• /
• pp.885-895
• /
• 1994

This study was performed to compare the dental arch dimensions of urban and rural high school females according to the region of residence and facial type. A model and cephalometric analysis was made from 48 urban and 48 rural high school females. The results of this study were obtained as follows : 1. Arch width in the urban group were similar to the rural group. 2. Lingual arch length at upper 1st premolar level in the urban group was larger than the rural group and lingual arch length at lower canine level in rural group was larger than the urban group. 3. Palatal height at canine level in the rural group was higher than the urban group. 4. Palatal heights at 2nd premolar and 1st molar level had correlation with the VERT index. In comparison of lingual arch dimensions according to Rickett's facial group, palatal heights at 2nd premolar and 1st molar level in dolichofacial group were lower than other groups.

• 대한두개안면성형외과학회지
• /
• 제22권3호
• /
• pp.135-140
• /
• 2021

Background: Wide surgical excision is the gold standard for basal cell carcinoma (BCC) treatment. Typically, resection requires a safety margin ≥ 4 mm. We aimed to confirm BCC excisions' cancer recurrence rate and safety on the facial region with new safety margins. Methods: We included patients with primary BCC on the facial region who underwent wide excision with 2- or 3-mm safety margins at our institution between January 2010 and December 2018. Medical records were reviewed to confirm the epidemiology and surgical information. Recurrence was confirmed by physical examination through regular 6-month follow-up. Results: We included 184 out of 233 patients in this study after applying the exclusion criteria. The mean age and follow-up period were 71.2±10.2 years and 29.3±13.5 months, respectively. The predominantly affected area was the nose (95 cases); a V-Y advancement flap was the most commonly used surgical method. There were two cases of recurrence in the 2 mm margin group and one recurrence in the group resected with 3 mm margins. Conclusion: In this large cohort study, we found 2-3 mm excision margins can yield enough safety in facial BCCs. The recurrence rates were found to be comparable with those reported after wider margins.

• Imaging Science in Dentistry
• /
• 제41권1호
• /
• pp.39-42
• /
• 2011

Facial asymmetry is not an uncommon occurrence in day to day dental practice. It can be caused by various etiologic factors ranging from facial trauma to serious hereditary conditions. Here, we report a rare case of non-syndromic facial asymmetry in a young female, who was born with this condition but was not aware of the progression of asymmetry. No relevant family history was recognized. She was also deficient in both deciduous and permanent teeth in the corresponding region of maxilla. Hence, the cause of this asymmetry was believed to be a segmental odontomaxillary hypoplasia of left maxilla accompanied by agenesis of left maxillary premolars and molars and disuse atrophy of corresponding facial musculature. This report briefly discussed the comparative features of segmental odontomaxillary hypoplasia, hemimaxillofacial dysplasia, and segmental odontomaxillary dysplasia and justified the differences between segmental odontomaxillary hypoplasia and the other two conditions.

• 한국컴퓨터정보학회논문지
• /
• 제7권4호
• /
• pp.46-51
• /
• 2002

본 논문은 얼굴 요소 중 눈썹을 검출하기 위한 기법으로, 눈썹은 얼굴 인식이나 표정 인식, 얼굴 애니메이션에 중요한 역할을 하는 요소이다. 색상 영역 분할을 통해 얼굴 영역을 검출한 다음, 형판 정합(template matching)을 통해 눈을 검출한다. 눈썹은 눈 바로 위에 위치하므로 검출된 눈의 위치 값을 이용하여 눈썹 후보 영역을 설정한다. 이렇게 설정된 눈썹 후보 영역에서 휘도(luminance) 성분의 히스토그램을 구한 다음, 이 히스토그램을 이용하여 thresholding 기법으로 눈썹을 검출한다. 일반적으로 이런 히스토그램은 하나의 bin을 갖는 peak나 valley가 무수히 많아 threshold 간을 결정하는데 어려움이 있다. 이런 어려움을 극복하고 좀더 쉽게 threshold 값을 찾기 위해 이런 peak나 valley를 제거해 히스토그램을 변형한다. 제안된 알고리즘은 얼굴 영역 검출부, 얼굴 요소 검출부, 그리고 FCP 추출부 등의 세 부분으로 구성되어있다.

• 대한전자공학회논문지SP
• /
• 제47권5호
• /
• pp.175-182
• /
• 2010

본 논문에서는 얼굴과 동공을 검색하는 새로운 기법을 제시하며, 안전운행을 위한 운전자의 동공 감시에 적용한 실험결과를 포함하고 있다. 제시된 기법은 세 단계 주요 과정을 거치는데, 먼저 스킨칼라 세그먼테이션 기법으로 얼굴을 찾는 과정으로 이는 지금까지 사용된 휴리스틱모델이 아닌 학습과정 모델에 기반을 두고 있다. 다음에 얼굴 특징 세그먼테이션으로 눈, 입, 눈썹 등의 부분을 검출 하는데, 이를 위해 얼굴 각 부분에서 추출한 고유 특징들에 대한 PDF 추정을 사용하고 있다. 마지막으로 서큘러 하프 변환기법으로 눈 안의 동공을 찾아낸다. 제시된 기법을 조명이 다른 웹 얼굴 영상과 운전자의 CCD 얼굴 영상에 적용하여 동공을 찾아내는 실험을 하여, 높은 동공 검출율을 확인하였다.